© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3772
    Prev
    Next
    INDEX
    Explanations

    constant or consistent states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     always
    0.80
     zawsze
    0.80
    er
    0.79
    总是
    0.78
    <bos>
    0.74
    בא
    0.74
     رش
    0.73
    antas
    0.72
     Sachen
    0.71
    দ
    0.70
    POSITIVE LOGITS
    emente
    1.12
    柢
    1.06
     threaten
    1.06
     옳은
    1.04
    瑆
    1.02
     reminder
    0.98
     proteinuria
    0.98
    BackPressed
    0.96
    reminder
    0.96
     Invalid
    0.96
    Activations Density 0.367%

    No Known Activations